© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18429
    Prev
    Next
    INDEX
    Explanations

    视

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ציג
    -0.09
    есті
    -0.09
    тың
    -0.09
    ertos
    -0.09
    édi
    -0.09
     organisaties
    -0.08
    osť
    -0.08
    тардың
    -0.08
    ement
    -0.08
    тарды
    -0.08
    POSITIVE LOGITS
     case
    0.10
    Case
    0.10
    角
    0.09
    线
    0.09
    野
    0.09
    lumbr
    0.09
    	case
    0.09
    point
    0.09
    Caso
    0.09
    -case
    0.08
    Activations Density 0.002%

    No Known Activations